Pytorch/Tensorflow detecting false objects

Hey,

I am a little bit new with Jetson and getting strange errors using Pytorch and Tensorflow with Python. Its detecting after a while classes which are not existing. And draw them at the next thread again and again on other positions. Please see my attached images.

We ara using same code at Windows and MacOS without problems. So i thin i have a problem with my packages?

My Python packages

absl-py 1.4.0
apturl 0.5.2
astor 0.8.1
asttokens 2.2.1
astunparse 1.6.3
backcall 0.2.0
bcrypt 3.1.7
blinker 1.4
boto3 1.26.145
botocore 1.29.145
Brlapi 0.7.0
cachetools 5.3.1
certifi 2022.12.7
cffi 1.15.1
chardet 4.0.0
charset-normalizer 3.1.0
Click 7.0
colorama 0.4.3
contourpy 1.0.7
cryptography 2.8
cupshelpers 1.0
cycler 0.10.0
Cython 0.29.35
dbus-python 1.2.16
decorator 4.4.2
defer 1.0.6
distlib 0.3.6
distro 1.4.0
distro-info 0.23ubuntu1
duplicity 0.8.12.0
entrypoints 0.3
executing 1.2.0
fasteners 0.14.1
filelock 3.12.0
fire 0.5.0
flatbuffers 23.5.26
fonttools 4.39.4
fsspec 2023.5.0
future 0.18.2
gast 0.3.3
gitdb 4.0.10
GitPython 3.1.31
google-auth 2.19.1
google-auth-oauthlib 0.4.6
google-pasta 0.2.0
graphsurgeon 0.4.6
grpcio 1.54.2
h5py 2.10.0
httplib2 0.14.0
huggingface-hub 0.15.1
idna 2.10
importlib-metadata 6.6.0
importlib-resources 5.12.0
ipython 8.12.2
jedi 0.18.2
Jetson.GPIO 2.0.21
jetson-stats 4.2.1
Jinja2 3.1.2
jmespath 1.0.1
keras 2.11.0
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.2
keyring 18.0.1
kiwisolver 1.4.4
language-selector 0.1
launchpadlib 1.10.13
lazr.restfulclient 0.14.2
lazr.uri 1.0.3
libclang 16.0.0
lockfile 0.12.2
louis 3.12.0
macaroonbakery 1.3.1
Mako 1.1.0
Markdown 3.4.3
MarkupSafe 2.1.2
matplotlib 3.7.1
matplotlib-inline 0.1.6
monotonic 1.5
mpmath 1.3.0
networkx 3.1
ngrok 0.8.1
numpy 1.23.5
oauthlib 3.1.0
olefile 0.46
onboard 1.4.1
onnx 1.14.0
onnx-graphsurgeon 0.3.12
opencv-python 4.7.0.72
opt-einsum 3.3.0
packaging 23.1
pandas 2.0.2
paramiko 2.6.0
parso 0.8.3
pexpect 4.6.0
pickleshare 0.7.5
Pillow 9.5.0
pip 23.1.2
platformdirs 3.5.1
prompt-toolkit 3.0.38
protobuf 3.20.2
psutil 5.9.5
pure-eval 0.2.2
pyasn1 0.5.0
pyasn1-modules 0.3.0
PyAudio 0.2.11
pybboxes 0.1.6
pycairo 1.16.2
pycparser 2.21
pycrypto 2.6.1
pycups 1.9.73
Pygments 2.15.1
PyGObject 3.36.0
PyJWT 1.7.1
pylibjpeg-libjpeg 1.3.4
pymacaroons 0.13.0
PyNaCl 1.3.0
pyparsing 2.4.7
pyRFC3339 1.1
pyshine 0.0.9
python-apt 2.0.0+ubuntu0.20.4.8
python-dateutil 2.8.2
python-dbusmock 0.19
python-debian 0.1.36ubuntu1
python-dotenv 1.0.0
pytz 2023.3
pyxdg 0.26
PyYAML 5.3.1
requests 2.31.0
requests-oauthlib 1.3.1
requests-toolbelt 1.0.0
requests-unixsocket 0.2.0
roboflow 1.0.9
rsa 4.9
s3transfer 0.6.1
sahi 0.11.14
scipy 1.10.1
seaborn 0.12.2
SecretStorage 2.3.1
setuptools 67.8.0
shapely 2.0.1
simplejson 3.16.0
six 1.14.0
smbus2 0.4.2
smmap 5.0.0
sounddevice 0.4.6
soundfile 0.12.1
stack-data 0.6.2
sympy 1.12
systemd-python 234
tensorboard 2.11.2
tensorboard-data-server 0.6.1
tensorboard-plugin-wit 1.8.1
tensorflow 2.11.0+nv23.3
tensorflow-estimator 2.11.0
tensorrt 8.5.2.2
termcolor 2.3.0
terminaltables 3.1.10
thop 0.1.1.post2209072238
torch 2.0.0+nv23.5
torchvision 0.15.1
tqdm 4.65.0
traitlets 5.9.0
typing_extensions 4.6.3
tzdata 2023.3
ubuntu-advantage-tools 27.12
ubuntu-drivers-common 0.0.0
uff 0.6.9
ultralytics 8.0.112
unicode 2.9
Unidecode 1.3.6
urllib3 1.26.16
urwid 2.0.1
virtualenv 20.23.0
wadllib 1.3.3
wcwidth 0.2.6
Werkzeug 2.3.4
wget 3.2
wheel 0.34.2
wrapt 1.15.0
xkit 0.0.0
yolov5 7.0.12
zipp 3.15.0

Hope you can help me.

Hi,

Have you changed anything when moving the code to the Jetson?
For example, the inference frameworks or camera pre-processing?

Thanks.

Hi,

no, nothing. I flashed again and reinstalled everything but nothing helped…

What is currently the latest stable release for Xavier? Maybe it helps to flash it again? I have actually 5.1.

Thanks

Hi,

Do you use an identical source compared to the desktop?
Any changing in the camera, or pre-processing?
These are the common cause of the different outputs.

The current latest software is JetPack 5.1.1.
Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.